Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 973
    Prev
    Next
    INDEX
    Explanations

    C

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nedenle
    0.71
    EL
    0.71
    หนังสือ
    0.66
    Ḩ
    0.66
     நன்றி
    0.65
    ال
    0.65
     ³
    0.65
    ৩৭
    0.64
    طنين
    0.64
     soient
    0.64
    POSITIVE LOGITS
    𝗸
    0.77
    ය
    0.71
    銖
    0.71
    មក
    0.68
     éste
    0.66
     tossing
    0.64
    鐫
    0.64
     formally
    0.63
    ჭირ
    0.63
     यानि
    0.63
    Activations Density 0.005%

    No Known Activations